### Resumen

In this work we present different learning strategies focused on detecting candidate solutions that are not interesting to be explored by a metaheuristic, in terms of evaluation function. We include a first step before the metaheuris-tic. The information obtained from this step is given to the metaheuristic, for visiting candidate solutions that are more promising in terms of their quality. The goal of using these strategies is to learn about candidate solutions that can be discarded from the search space, and thus to improve the search of the metaheuristic. We present two new strategies that differ on how the solutions can be constructed in an opposite way. Our approach is evaluated using Ant Solver, a well-known ant based algorithm for solving Constraint Satisfaction Problems. We show promising results that make our solution as good approach to apply in other metaheuristics.

Idioma original | English |
---|---|

Título de la publicación alojada | GECCO 2016 - Proceedings of the 2016 Genetic and Evolutionary Computation Conference |

Editores | Tobias Friedrich |

Editorial | Association for Computing Machinery, Inc |

Páginas | 389-396 |

Número de páginas | 8 |

ISBN (versión digital) | 9781450342063 |

DOI | |

Estado | Published - 20 jul 2016 |

Evento | 2016 Genetic and Evolutionary Computation Conference, GECCO 2016 - Denver, United States Duración: 20 jul 2016 → 24 jul 2016 |

### Conference

Conference | 2016 Genetic and Evolutionary Computation Conference, GECCO 2016 |
---|---|

País | United States |

Ciudad | Denver |

Período | 20/07/16 → 24/07/16 |

### Huella dactilar

### ASJC Scopus subject areas

- Computer Science Applications
- Computational Theory and Mathematics
- Software

### Citar esto

*GECCO 2016 - Proceedings of the 2016 Genetic and Evolutionary Computation Conference*(pp. 389-396). Association for Computing Machinery, Inc. https://doi.org/10.1145/2908812.2908927

}

*GECCO 2016 - Proceedings of the 2016 Genetic and Evolutionary Computation Conference.*Association for Computing Machinery, Inc, pp. 389-396, 2016 Genetic and Evolutionary Computation Conference, GECCO 2016, Denver, United States, 20/07/16. https://doi.org/10.1145/2908812.2908927

**Ants can learn from the opposite.** / Rojas-Morales, Nicolás; María-Cristina, Riff R.; Montero, Elizabeth.

Resultado de la investigación: Conference contribution

TY - GEN

T1 - Ants can learn from the opposite

AU - Rojas-Morales, Nicolás

AU - María-Cristina, Riff R.

AU - Montero, Elizabeth

PY - 2016/7/20

Y1 - 2016/7/20

N2 - In this work we present different learning strategies focused on detecting candidate solutions that are not interesting to be explored by a metaheuristic, in terms of evaluation function. We include a first step before the metaheuris-tic. The information obtained from this step is given to the metaheuristic, for visiting candidate solutions that are more promising in terms of their quality. The goal of using these strategies is to learn about candidate solutions that can be discarded from the search space, and thus to improve the search of the metaheuristic. We present two new strategies that differ on how the solutions can be constructed in an opposite way. Our approach is evaluated using Ant Solver, a well-known ant based algorithm for solving Constraint Satisfaction Problems. We show promising results that make our solution as good approach to apply in other metaheuristics.

AB - In this work we present different learning strategies focused on detecting candidate solutions that are not interesting to be explored by a metaheuristic, in terms of evaluation function. We include a first step before the metaheuris-tic. The information obtained from this step is given to the metaheuristic, for visiting candidate solutions that are more promising in terms of their quality. The goal of using these strategies is to learn about candidate solutions that can be discarded from the search space, and thus to improve the search of the metaheuristic. We present two new strategies that differ on how the solutions can be constructed in an opposite way. Our approach is evaluated using Ant Solver, a well-known ant based algorithm for solving Constraint Satisfaction Problems. We show promising results that make our solution as good approach to apply in other metaheuristics.

KW - Ant algorithms

KW - Antipheromone

KW - Negative pheromone

KW - Opposite learning strategies

UR - http://www.scopus.com/inward/record.url?scp=84985914541&partnerID=8YFLogxK

U2 - 10.1145/2908812.2908927

DO - 10.1145/2908812.2908927

M3 - Conference contribution

SP - 389

EP - 396

BT - GECCO 2016 - Proceedings of the 2016 Genetic and Evolutionary Computation Conference

A2 - Friedrich, Tobias

PB - Association for Computing Machinery, Inc

ER -